Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    movement and return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '?
    -0.06
     Nederland
    -0.06
     stopping
    -0.06
    parts
    -0.06
     tame
    -0.06
     uf
    -0.06
     hob
    -0.06
    .Zero
    -0.06
     ges
    -0.06
     Humans
    -0.06
    POSITIVE LOGITS
    =$((
    0.07
    _res
    0.07
    xCB
    0.06
    oslav
    0.06
    ической
    0.06
    َة
    0.06
    .IsNullOrEmpty
    0.06
    _reduce
    0.06
    _secondary
    0.06
     전국
    0.06
    Act Density 0.134%

    No Known Activations